Crimson
A high-performance language model architecture.
🌹 Overview
Crimson is a generative language model that deviates from the traditional Transformer architecture by utilizing a hybrid approach of Local and Global Convolutions. By leveraging Fast Fourier Transforms (FFT) for global context, Crimson achieves a massive receptive field with a fraction of the computational overhead associated with standard attention mechanisms.
The architecture is designed for efficiency, speed, and high-quality generation, featuring a custom vocabulary reduction system that optimizes the embedding space for specific datasets.
📦 Installation
Download this repository and extract it.
Usage
1. Training the Model
Place your .txt data files in the data/ directory and run:
python train_crimson.py
This script will build the vocabulary and train the foundation model
2. Interactive Chat Interface
Launch the Tkinter-based UI to interact with your model:
python chat_interface.py
Fine-tuning
You may fine-tune the model by resuming training from a checkpoint, you may use a different dataset as long as the vocabulary is the same, you may also change parameters such as the learning rate, batch size, etc.
Built with ❤️ by AG